Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization
Autor: | Min Sun, Shih-Han Chou, Kuo-Hao Zeng, Fu-Hsiang Chan, Juan Carlos Niebles |
---|---|
Rok vydání: | 2017 |
Předmět: |
FOS: Computer and information sciences
Risk analysis business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Machine learning computer.software_genre 03 medical and health sciences Accident (fallacy) 0302 clinical medicine Anticipation (artificial intelligence) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Risk assessment computer 030217 neurology & neurosurgery Risk management Event (probability theory) |
Zdroj: | CVPR |
DOI: | 10.1109/cvpr.2017.146 |
Popis: | For survival, a living agent (e.g., human in Fig. 1(a)) must have the ability to assess risk (1) by temporally anticipating accidents before they occur (Fig. 1(b)), and (2) by spatially localizing risky regions (Fig. 1(c)) in the environment to move away from threats. In this paper, we take an agent-centric approach to study the accident anticipation and risky region localization tasks. We propose a novel soft-attention Recurrent Neural Network (RNN) which explicitly models both spatial and appearance-wise non-linear interaction between the agent triggering the event and another agent or static-region involved. In order to test our proposed method, we introduce the Epic Fail (EF) dataset consisting of 3000 viral videos capturing various accidents. In the experiments, we evaluate the risk assessment accuracy both in the temporal domain (accident anticipation) and spatial domain (risky region localization) on our EF dataset and the Street Accident (SA) dataset. Our method consistently outperforms other baselines on both datasets. |
Databáze: | OpenAIRE |
Externí odkaz: |